DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Are AI Tools Actually Making Us Productive — or Just Giving Us Something New to Play With?

The courier problem of manual tab-hopping
james_anderson_h profile

Are AI Tools Actually Making Us Productive — or Just Giving Us Something New to Play With?

#ai #productivity #llm #webdev
23
Comments 34
8 min read
Your LLM App Is Wasting Money: What Happens When Users Close the Tab?
kristinz profile

Your LLM App Is Wasting Money: What Happens When Users Close the Tab?

#ai #llm #typescript #agents
6
Comments 10
9 min read
The harness, not the model: how to make a weak or local model reliable enough to ship
abishaiama profile

The harness, not the model: how to make a weak or local model reliable enough to ship

#ai #llm #localagents #agents
1
Comments 4
7 min read
What if the main coding-agent session was intentionally dumb?
justjov profile

What if the main coding-agent session was intentionally dumb?

#agents #ai #coding #llm
Comments
1 min read
I built a prompt injection firewall in Rust. It scans in 12 microseconds.
tim860 profile
Tim

I built a prompt injection firewall in Rust. It scans in 12 microseconds.

#rust #security #python #llm
1
Comments 30
4 min read
Aletheia: What If AI Stopped Trying to Be Your Answer?
alirezaai profile

Aletheia: What If AI Stopped Trying to Be Your Answer?

#ai #llm #github #development
1
Comments
6 min read
MarathonMemBench — a new kind of benchmark for testing your LLM agent's memory
alexander_ovsov_f85e6b68f profile

MarathonMemBench — a new kind of benchmark for testing your LLM agent's memory

#agents #ai #llm #testing
1
Comments 3
42 min read
I asked ChatGPT and Grok to benchmark my game AI. Then I ran the code.
lucian_lkb_1f009d profile

I asked ChatGPT and Grok to benchmark my game AI. Then I ran the code.

#ai #llm #algorithms #gamedev
2
Comments 1
3 min read
How to Read Benchmark Tables: A Case Study of GigaChat 3.5 "Ultra Reasoning" vs DeepSeek V4 Flash
toxy4ny profile

How to Read Benchmark Tables: A Case Study of GigaChat 3.5 "Ultra Reasoning" vs DeepSeek V4 Flash

#ai #machinelearning #llm #benchmarks
16
Comments 2
15 min read
Local LLMs in 2026: What Actually Runs Well on a Laptop Now
ai_maya_063fc568e157562fd profile

Local LLMs in 2026: What Actually Runs Well on a Laptop Now

#ai #llm #machinelearning #tutorial
Comments
3 min read
The Model Scored 30%. The Harness Scored 100%. Which One Did You Benchmark?

Harnesses drive massive score jumps
p0rt profile

The Model Scored 30%. The Harness Scored 100%. Which One Did You Benchmark?

#ai #llm #agents #machinelearning
23
Comments 49
10 min read
Case study: smart-proxy
devbrewery profile

Case study: smart-proxy

#ai #llm #architecture #python
1
Comments 3
6 min read
12 Agentic Harness Patterns
akki907 profile

12 Agentic Harness Patterns

#ai #agents #llm #mcp
2
Comments 3
6 min read
Sending Images to GPT-4o, Claude, and Gemini: The Base64 Payload Each One Wants
pjanderson profile

Sending Images to GPT-4o, Claude, and Gemini: The Base64 Payload Each One Wants

#ai #claude #llm #openai
Comments
4 min read
You can never backfill a read receipt: a blog comment fixed our AI pipeline
gxcafellc profile

You can never backfill a read receipt: a blog comment fixed our AI pipeline

#ai #llm #agents #devops
Comments 2
3 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.